-
Information, Inference, and Privacy
Mon, Mar 23, 2015 @ 11:00 AM - 12:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Flavio du Pin Calmon, MIT
Talk Title: Information, Inference, and Privacy
Abstract: Widespread collection of data has led to new and challenging privacy and security risks. There is a need to engineer mechanisms that allow users to selectively disclose their data to a third party in order to achieve a utility goal (e.g. receive high quality product recommendations), while restricting the release of private information (e.g. not revealing a given medical condition). In this talk, we use tools from information theory, statistics and estimation theory to characterize the fundamental limits of estimation when only partial statistics of the data are known. We then apply the insight gained by characterizing these limits to quantify the fundamental privacy-utility tradeoff and to design privacy-assuring mechanisms.
In addition, we introduce security metrics and associated results based on the spectrum of the conditional expectation operator, called the principal inertia components. The principal inertia components allow a fine-grained decomposition of the dependence between a hidden and an observed variable which, in turn, is useful for deriving fundamental bounds for estimation problems, and for measuring information leakage in secure communication models. Finally, we illustrate how our results can be used as a design driver for applications in security, noisy computation and distributed systems.
Biography: Flavio du Pin Calmon is a PhD candidate in Electrical Engineering and Computer Science (with a minor in Mathematics) at MIT, and a member of the Network Coding and Reliable Communications Group at the Research Laboratory of Electronics (RLE). His research interests include information theory, statistics, estimation theory, security and privacy. In addition to his work at MIT, Flavio has ongoing collaborations with the MIT Lincoln Laboratory, Technicolor SA and NetApp. Before coming to MIT, he received an M.Sc. in Electrical Engineering from the Universidade Estadual de Campinas, Brazil, and a B.Sc. in Communications Engineering from the Universidade de Brasilia, Brazil.
Host: Andreas Molisch
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Gerrielyn Ramos